Minsoo Ha
Minsoo Ha (하민수)
M.S. student in Artificial Intelligence
Pohang University of Science and Technology (POSTECH)
haminsoo0926 [at] gmail [dot] com

I am an MS student at POSTECH GSAI (Graduate School of AI). I am currently doing research at the Interactive Machine Learning Lab advised by Prof. Kwang-Sung Jun.

My research interests lie in Statistical learning theory, Interactive machine learning, and the algorithmic foundations of machine learning algorithms. I am especially drawn to problems where mathematical structure can be used to make learning systems more reliable and provably correct.

Alongside my research, I am deeply interested in software engineering and passionate about building products that deliver real-world impact. In line with this commitment, I am was building a service KnowGem, a knowledge-graph workspace for hallucination-free reasoning over documents.

News

Sep 2026 Started M.S. degree at POSTECH Graduate School of AI (advisor: Prof. Kwang-Sung Jun).
Apr 2026 Joined the Interactive Machine Learning Lab @ POSTECH as an undergraduate research assistant (advisor: Prof. Kwang-Sung Jun).
Sep 2025 Started research at the ML Lab @ POSTECH on LLM reasoning & RL (advisor: Prof. Sangdon Park).
Jan 2025 Joined LinqAlpha as a Fundamental Research Engineer, working on RAG for finance, Text-to-SQL, and STT workflows.
Aug 2024 Joined FBA Quant, applying ML methods to quantitative finance.
Oct 2023 Completed military service (ROK Army, reserve training instructor).
Feb 2020 Began B.S. in Mathematics @ POSTECH.

Research & Projects

KnowGem
A focused workspace that turns scattered documents into a navigable graph context and validates reasoning outputs with Higher-Order Logic. Aims to enable hallucination-free, deductive reasoning grounded in symbolic structure.
project page · Express.js, React, Supabase, AWS, Terraform
PPO
A clean, from-scratch PyTorch implementation of PPO compatible with the Gymnasium API, supporting both discrete and continuous control.
code · PyTorch, Gymnasium
DRL Portfolio
A portfolio-optimization system that learns allocation policies with PPO under diverse simulated market regimes, served through a FastAPI training/evaluation UI.
code · PyTorch, Stable-Baselines3, FastAPI

Service

Education